About
This comprehensive course guides participants through the complete geospatial data workflow from foundational GIS and remote sensing concepts to advanced AI-driven analysis. Learners will explore raster and vector data, spectral bands, and projections using QGIS and ArcGIS, followed by hands-on experience in data acquisition from platforms like Google Earth Engine (GEE), Copernicus Open Access Hub, and OpenStreetMap. The course emphasizes preprocessing techniques (atmospheric correction, mosaicking, cloud masking) and image classification (supervised, unsupervised) using Python, SCP, and GEE. Participants will advance to applying machine learning and deep learning models including Random Forest, XGBoost, LSTM, and CNNs for environmental monitoring, vegetation health, hazard mapping, and land cover change detection. Specialized modules cover SAR data processing, InSAR deformation studies, and object detection using YOLO, Detectron2, and DeepForest. The course concludes with time-series analysis, visualization, and storytelling, empowering learners to build interactive maps and dashboards in Mapbox, Kepler.gl, and Power BI. Designed for researchers, professionals, and students in geoscience, ecology, and environmental management, this course equips participants with practical, modern geospatial analysis skills for data-driven decision-making.